ICML

Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation

Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew Saxe

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:12455-12477 (2022)

The dynamics of representation learning in shallow, non-linear autoencoders

Maria Refinetti, Sebastian Goldt

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:18499-18519 (2022)

Stochastic Parallelizable Eigengap Dilation for Large Graph Clustering

Elise van der Pol, Ian Gemp, Yoram Bachrach, Richard Everett

Comments Presented at the ICML 2022 Workshop on Topology, Algebra, andGeometry in Machine Learning

Adaptive Second Order Coresets for Data-efficient Machine Learning

Omead Pooladzandi, David Davini, Baharan Mirzasoleiman

Journal ref International Conference on Machine Learning 2022

Exploiting and Defending Against the Approximate Linearity of Apple's NeuralHash

Jagdeep Singh Bhatia, Kevin Meng

Comments Accepted to the ML4Cyber Workshop at ICML 2022

Language Model Cascades

David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A. Saurous, Jascha Sohl-dickstein, Kevin Murphy, Charles Sutton

Comments Presented as spotlight at the Beyond Bases workshop at ICML 2022 (https://beyond-bayes.github.io)

An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees

Guillaume Braun, Hemant Tyagi, Christophe Biernacki

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:2257-2291, 2022

Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms

Baturay Saglam, Dogan C. Cicek, Furkan B. Mutlu, Suleyman S. Kozat

Comments ICML 2022 Workshop on Responsible Decision Making in Dynamic Environments (poster: http://responsibledecisionmaking.github.io/assets/poster/19.pdf , presentation: http://drive.google.com/file/d/1vjjMh_z51xdOjsQCcGfU5ojAcrrf3dOS/view?usp=sharing )

Universality of Winning Tickets: A Renormalization Group Perspective

William T. Redman, Tianlong Chen, Zhangyang Wang, Akshunna S. Dogra

Comments 16 pages, 3 figures, 8 tables

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR Vol. 162, pp. 18483-18498 (ICML 2022)

Scalable Certified Segmentation via Randomized Smoothing

Marc Fischer, Maximilian Baader, Martin Vechev

Comments ICML'21

Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety

Puja Trivedi, Danai Koutra, Jayaraman J. Thiagarajan

Comments Principles of Distribution Shift (PODS) Workshop at ICML 2022, 4 pages, 2 figures

The Bearable Lightness of Big Data: Towards Massive Public Datasets in Scientific Machine Learning

Wai Tong Chung, Ki Sung Jung, Jacqueline H. Chen, Matthias Ihme

Comments Accepted in ICML 2022 2nd AI for Science Workshop. 10 pages, 8 figures

Journal ref ICML 2022 2nd AI for Science Workshop

Bayesian tensor factorization for predicting clinical outcomes using integrated human genetics evidence

Onuralp Soylemez

Comments ICML 2022, Workshop on Computational Biology

Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions

Shuang Qiu, Xiaohan Wei, Jieping Ye, Zhaoran Wang, Zhuoran Yang

Comments ICML 2021

Automated discovery of interpretable gravitational-wave population models

Kaze W. K Wong, Miles Cranmer

Comments Published in ML4Astro Workshop at ICML 2022. 8 pages, 1 figure. Code at https://github.com/kazewong/SymbolicGWPopulation_paper

Implicit Regularization with Polynomial Growth in Deep Tensor Factorization

Kais Hariz, Hachem Kadri, Stéphane Ayache, Maher Moakher, Thierry Artières

Comments Accepted to ICML 2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022

Unsupervised Image Representation Learning with Deep Latent Particles

Tal Daniel, Aviv Tamar

Comments ICML 2022. Project webpage and code: https://taldatech.github.io/deep-latent-particles-web/

Journal ref Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:4644-4665 (2022)

Variational Inference with Locally Enhanced Bounds for Hierarchical Models

Tomas Geffner, Justin Domke

Comments Presented at ICML 2022

An Adaptive Deep Clustering Pipeline to Inform Text Labeling at Scale

Xinyu Chen, Ian Beaver

Comments Presented at DataPerf 2022 Workshop at ICML 2022. arXiv admin note: substantial text overlap with arXiv:2202.00802

A Regret Minimization Approach to Multi-Agent Control

Udaya Ghai, Udari Madhushani, Naomi Leonard, Elad Hazan

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:7422-7434, 2022

Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning

Utku Evci, Vincent Dumoulin, Hugo Larochelle, Michael C. Mozer

Comments presented at ICML 2022 (Oral)

Journal ref ICML 2022, Proceedings of the 39th International Conference on Machine Learning

Modeling Irregular Time Series with Continuous Recurrent Units

Mona Schirmer, Mazin Eltayeb, Stefan Lessmann, Maja Rudolph

Comments Accepted at ICML 2022, Baltimore, Maryland

Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools

Davis Brown, Henry Kvinge

Comments AdvML Frontiers 2022 @ ICML 2022 workshop

MAPIE: an open-source library for distribution-free uncertainty quantification

Vianney Taquet, Vincent Blot, Thomas Morzadec, Louis Lacombe, Nicolas Brunel

Comments Submitted to the 2022 ICML workshop "Distribution-free uncertainty quantification"

COEM: Cross-Modal Embedding for MetaCell Identification

Haiyi Mao, Minxue Jia, Jason Xiaotian Dou, Haotian Zhang, Panayiotis V. Benos

Comments 5 pages, 2 figures, ICML workshop on computational biology

Comparing supervised and self-supervised embedding for ExVo Multi-Task learning track

Tilak Purohit, Imen Ben Mahmoud, Bogdan Vlasenko, Mathew Magimai. -Doss

Journal ref Proceedings of the ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts

A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks

Yu Pan, Zeyong Su, Ao Liu, Jingquan Wang, Nannan Li, Zenglin Xu

Comments Accepted in ICML 2022

Scaling Structured Inference with Randomization

Yao Fu, John P. Cunningham, Mirella Lapata

Comments ICML 2022 camera ready

Time Series Prediction under Distribution Shift using Differentiable Forgetting

Stefanos Bennett, Jase Clarkson

Comments ICML Principles of Distribution Shift 2022 Workshop

Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers

Björn Lütjens, Catherine H. Crawford, Campbell D Watson, Christopher Hill, Dava Newman

Comments Presented at International Conference on Machine Learning Workshop AI for Science, 2022